Neural network-aided unsupervised input function estimation for dual-time-window PET Patlak analysis
We demonstrate the feasibility of using a weighted statistic, constructed from a multi-branch neural network, to accurately estimate the complete IF. This approach enables the generation of high-quality parametric images with shortened scan protocols, effectively reducing scanning time while ensuring accurate Patlak analysis.
Authors
- Zhaoheng Xie (ORCID: https://orcid.org/0000-0001-8003-8778)
- Yarong Zhang
- Fangxiao Cheng (ORCID: https://orcid.org/0000-0002-8768-2870)
- Xiangxi Meng (ORCID: https://orcid.org/0000-0002-6590-011X)
- Ying Liang (ORCID: https://orcid.org/0000-0001-9092-2110)
- Fen Du (ORCID: https://orcid.org/0000-0002-5862-4989)
- Wenrui Shao
- Yixin Chen (ORCID: https://orcid.org/0000-0002-2727-6387)
Institutions
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Peking University (CN)
- National Cancer Center (US)
- Ministry of Education (ET)
Publication Details
- Journal
- EJNMMI Physics
- Published
- 2025-12-08
- DOI
- https://doi.org/10.1186/s40658-025-00804-w
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00